ninagroot/Llama-360Mtest

README.md

@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.8874
+- Loss: 3.8923
 
 ## Model description
 
@@ -48,14 +48,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 7.2772        | 1.0   | 57   | 5.2473          |
-| 4.5014        | 2.0   | 114  | 4.3679          |
-| 3.7043        | 3.0   | 171  | 4.0728          |
-| 3.2163        | 4.0   | 228  | 3.9930          |
-| 2.7737        | 5.0   | 285  | 3.9367          |
-| 2.3424        | 6.0   | 342  | 3.8971          |
-| 2.1244        | 7.0   | 399  | 3.8862          |
-| 1.9246        | 8.0   | 456  | 3.8874          |
+| 7.3196        | 1.0   | 57   | 5.3418          |
+| 4.5649        | 2.0   | 114  | 4.4289          |
+| 3.7241        | 3.0   | 171  | 4.0877          |
+| 3.2269        | 4.0   | 228  | 4.0008          |
+| 2.8044        | 5.0   | 285  | 3.9489          |
+| 2.3813        | 6.0   | 342  | 3.9084          |
+| 2.1508        | 7.0   | 399  | 3.8925          |
+| 1.9477        | 8.0   | 456  | 3.8923          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd848a0c9bb2f7fc524b6bd5ee487f0df63e74cad659bb4239c0566d8024e9ac
+oid sha256:c21ff9fd563fb26007d5336a6d8e14b43ffdf1ee2e9a1c51f85e4b00c6c6f311
 size 1570992472

runs/Apr02_14-53-04_gcn41.local.snellius.surf.nl/events.out.tfevents.1712062395.gcn41.local.snellius.surf.nl.1105566.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c236d584259dcb5ed977805b1d8c1095b8035e02588c18334bf0f0630b542ed
+size 11692

special_tokens_map.json

@@ -2,5 +2,11 @@
   "bos_token": "<s>",
   "eos_token": "</s>",
   "pad_token": "<pad>",
-  "unk_token": "<|endoftext|>"
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -1,8 +1,10 @@
 {
-  "add_prefix_space": false,
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -24,21 +26,17 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "4425": {
-      "content": "<|endoftext|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
+  "legacy": true,
   "model_max_length": 128,
   "pad_token": "<pad>",
-  "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>"
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e6f56c5033b4217ecac95a41fcc4c8552b7b9ce09eb144b008512cf0a392b02
+oid sha256:2edf2aafc57de033971a24441a97b4a8f411417a4f0e62b380ddc309fb76da3b
 size 4984